TMop: A tool for unsupervised Translation Memory cleaning

Abstract

We present TMop, the first open-source tool for automatic Translation Memory (TM) cleaning. The tool implements a fully unsupervised approach to the task, which allows spotting unreliable translation units (sentence pairs in different languages, which are supposed to be translations of each other) without requiring labeled training data. TMop includes a highly configurable and extensible set of filters capturing different aspects of translation quality. It has been evaluated on a test set composed of 1,000 translation units (TUs) randomly extracted from the English-Italian version of MyMemory, a large-scale public TM. Results indicate its effectiveness in automatic removing "bad" TUs, with comparable performance to a state-of-the-art supervised method (76.3 vs. 77.7 balanced accuracy).